arXiv · 2011.06709
Active Reinforcement Learning: Observing Rewards at a Cost
Abstract
Active reinforcement learning (ARL) is a variant on reinforcement learning where the agent does not observe the reward unless it chooses to pay a query cost c > 0. The central question of ARL is how to quantify the long-term value of reward information. Even in multi-armed bandits, computing the value of this information is intractable and we have to rely on heuristics. We propose and evaluate several heuristic approaches for ARL in multi-armed bandits and (tabular) Markov decision processes, and discuss and illustrate some challenging aspects of the ARL problem.
Explore related subjects
Keep this discovery
David Krueger, Jan Leike, Owain Evans, John Salvatier. 2020-11-13. Active Reinforcement Learning: Observing Rewards at a Cost. https://arxiv.org/abs/2011.06709
Cite the original work for its findings. Save a collection to share your selection of sources.